Tejas Khot

Papers

Total Citations

990

H-Index

About

Tejas Khot is a leading researcher in 3D computer vision and deep learning, whose work has fundamentally advanced the field of shape completion. He is best known as the primary author of the seminal "PCN: Point Completion Network," a landmark paper that has garnered over 990 citations. This work introduced a novel learning-based approach to infer the complete 3D geometry of objects from partial, often sparse, point cloud observations—a core challenge for robotics, autonomous driving, and augmented reality. By directly operating on raw point clouds and employing a coarse-to-fine generation strategy, PCN set a new standard for accuracy and efficiency in shape completion. Beyond this foundational contribution, Khot’s research explores the intersection of generative models and 3D perception, enabling machines to reason about occluded or unseen geometry. His work has been widely adopted in both academia and industry, influencing subsequent architectures for point cloud processing and 3D reconstruction. For students and researchers, Khot’s contributions exemplify how elegant, data-driven solutions can solve long-standing problems in visual understanding, making him a pivotal figure in modern 3D vision.